> ## Documentation Index
> Fetch the complete documentation index at: https://docs.riggery.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# AI

> Provider, API key, and model for this Instance.

Open an Instance and go to the **AI** tab. Agent nodes on the Graph use these settings.

Secrets never go to the model. The Agent only sees that a key is connected.

<h2 id="provider">
  Provider
</h2>

Where this Instance gets models:

* **Riggery** — curated catalog. Uses AI credits on your plan. Your own API key does not spend credits.
* **Your API key** — OpenAI, OpenRouter, or a compatible endpoint.
* **Ollama** — local models, when the app allows it.

<h2 id="model">
  Model
</h2>

Pick a model from the provider list. Vision, tools, and thinking follow what the catalog knows about that model.

<h2 id="api-key">
  API key
</h2>

For your own provider, bind a Secret. Do not paste keys into Chat or Settings text.

<h2 id="context">
  Context
</h2>

How much of the conversation the model can see at once. Leave empty to use the model default, within plan limits.